nneeno lars
1) and 2) the extremely dangerous was meant in connection with the webinterface security issue. And this was extremely dangerous.
3) Afaik a single process/thread cannot be split among diffrent cores through vmware. This means an single Process/thread runs a lot faster on an intel machine.
My application is single threaded and benefit from intel aesni.
Your support told me that they will move my vps to an intel machine and will install an current version of (english) debian x64.
btw. after i get my new vps details, i will review it too. (And possibly rent 9 more..)
Updated Review (now with Intel Processor):
Still old Version 6.0.4 in i386 (instead of 6.0.6 amd64), but it's now in english and i can upgrade to 6.0.6 (still i386 but okay..).
IP: 178.32.231.11 ("OVH_39364075")
ASN: AS16276 ("OVH")
=> Security issue is fixed, sources.list is still wrong and debian will be delivered in old version.
Latency:
Germany (10000mbit Business Connection):
from 10ms to 100ms. Seems this box is oversold.
Equinix Toronto:
iAdvantage Hong Kong:
Telehouse New York:
Bandwidth:
Cachefly:
Dropped from 25,4 MB/s to 1,85 MB/s. ... (really) BAD!
ftp.fr.debian.org:
Dropped from 38,2 MB/s to 3,71 MB/s .... BAD!
debian.cites.illinois.edu:
Dropped from 3,40 MB/s to 2,36 MB/s thats okay.
Performance:
Dropped from 26,3 MB/s to 14.6 MB/s
unixbench:
/proc/cpuinfo:
/proc/meminfo:
Like expected, CPU much faster, but node is obvisiously oversold and network is quiet bad
@ papillon :
Thanks to do a review of our host.
1) Root password are simple but not extremly dangerous, and customers have only to change password.
2) We have fix the security of the Webinterface
3) For the processor, if you really care about using a XEON and not an Opteron, no problem we can moving you vps when you want, but the core of the vps are virtual so, you can use 10Ghz if you want, it's not depend on AMD or Intel.
4) no problem for having more than one vps, but for particular orders, we ask to the customers why he want specials vps.
Best Regards,
1) and 2) the extremely dangerous was meant in connection with the webinterface security issue. And this was extremely dangerous.
3) Afaik a single process/thread cannot be split among diffrent cores through vmware. This means an single Process/thread runs a lot faster on an intel machine.
My application is single threaded and benefit from intel aesni.
Your support told me that they will move my vps to an intel machine and will install an current version of (english) debian x64.
btw. after i get my new vps details, i will review it too. (And possibly rent 9 more..)
Updated Review (now with Intel Processor):
Still old Version 6.0.4 in i386 (instead of 6.0.6 amd64), but it's now in english and i can upgrade to 6.0.6 (still i386 but okay..).
IP: 178.32.231.11 ("OVH_39364075")
ASN: AS16276 ("OVH")
=> Security issue is fixed, sources.list is still wrong and debian will be delivered in old version.
Latency:
Germany (10000mbit Business Connection):
Ping wird ausgeführt für 178.32.231.11 mit 32 Bytes Daten:
Antwort von 178.32.231.11: Bytes=32 Zeit=77ms TTL=249
Antwort von 178.32.231.11: Bytes=32 Zeit=93ms TTL=249
Antwort von 178.32.231.11: Bytes=32 Zeit=82ms TTL=249
Antwort von 178.32.231.11: Bytes=32 Zeit=100ms TTL=249
Ping-Statistik für 178.32.231.11:
Pakete: Gesendet = 4, Empfangen = 4, Verloren = 0
(0% Verlust),
Ca. Zeitangaben in Millisek.:
Minimum = 77ms, Maximum = 100ms, Mittelwert = 88ms
from 10ms to 100ms. Seems this box is oversold.
Equinix Toronto:
1 * * * ?
2 * * * ?
3 * * * ?
4 89 ms 89 ms 99 ms 91.121.128.193
5 123 ms * 98 ms 91.121.131.13
6 88 ms 91 ms 99 ms 91.121.130.201
7 212 ms 197 ms 202 ms 178.32.231.11# Entry cached for another 37 seconds.
iAdvantage Hong Kong:
1 191 ms 173 ms 173 ms 184.105.222.101
2 173 ms 175 ms 173 ms 72.52.92.122
3 250 ms 220 ms 201 ms 206.223.143.214
4 * 250 ms * 198.27.73.193
5 * * * ?
6 456 ms 317 ms 329 ms 91.121.131.181
7 347 ms 378 ms 321 ms 91.121.131.9
8 322 ms 312 ms 317 ms 91.121.130.73
9 424 ms 422 ms 410 ms 178.32.231.11# Entry cached for another 39 seconds.
Telehouse New York:
1 <1 ms <1 ms <1 ms 72.52.92.49
2 <1 ms * 3 ms 198.32.118.106
3 * 22 ms * 178.32.135.57
4 80 ms * * 198.27.73.31
5 81 ms 89 ms 82 ms 94.23.122.66
6 * 97 ms 81 ms 94.23.122.105
7 119 ms 80 ms 80 ms 91.121.130.73
8 190 ms 200 ms 200 ms 178.32.231.11# Entry cached for another 44 seconds.
Bandwidth:
Cachefly:
root@vps-144:~# wget http://cachefly.cachefly.net/100mb.test
--2013-02-21 22:28:03-- http://cachefly.cachefly.net/100mb.test
Saving to: â100mb.testâ
100%[===========================================================================================================================================================>] 104,857,600 2.79M/s in 54s
2013-02-21 22:28:58 (1.85 MB/s) - â100mb.testâ
Dropped from 25,4 MB/s to 1,85 MB/s. ... (really) BAD!
ftp.fr.debian.org:
root@vps-144:~# wget ftp://ftp2.fr.debian.org/pub/debian-cd/6.0.6/i386/iso-cd/debian-6.0.6-i386-netinst.iso
--2013-02-21 22:30:16-- ftp://ftp2.fr.debian.org/pub/debian-cd/6.0.6/i386/iso-cd/debian-6.0.6-i386-netinst.iso
Length: 200278016 (191M) (unauthoritative)
100%[===========================================================================================================================================================>] 200,278,016 5.97M/s in 51s
2013-02-21 22:31:08 (3.71 MB/s) - âdebian-6.0.6-i386-netinst.isoâ
Dropped from 38,2 MB/s to 3,71 MB/s .... BAD!
debian.cites.illinois.edu:
root@vps-144:~# wget http://debian.cites.illinois.edu/pub/debian-cd/6.0.6/i386/iso-cd/debian-6.0.6-i386-netinst.iso
--2013-02-21 22:32:16-- http://debian.cites.illinois.edu/pub/debian-cd/6.0.6/i386/iso-cd/debian-6.0.6-i386-netinst.iso
100%[===========================================================================================================================================================>] 200,278,016 3.60M/s in 81s
2013-02-21 22:33:37 (2.36 MB/s) - âdebian-6.0.6-i386-netinst.iso.1â
Dropped from 3,40 MB/s to 2,36 MB/s thats okay.
Performance:
root@vps-144:~# dd if=/dev/zero of=/home/2gb.dat bs=8k count=256k conv=fdatasync
262144+0 records in
262144+0 records out
2147483648 bytes (2.1 GB) copied, 146.634 s, 14.6 MB/s
Dropped from 26,3 MB/s to 14.6 MB/s
unixbench:
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: vps-144: GNU/Linux
OS: GNU/Linux -- 2.6.32-5-686 -- #1 SMP Mon Jan 16 16:04:25 UTC 2012
Machine: i686 (unknown)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz (6784.6 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT
22:41:12 up 1:02, 2 users, load average: 0.37, 0.46, 0.24; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Thu Feb 21 2013 22:41:12 - 23:09:25
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 22410640.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3409.7 MWIPS (10.1 s, 7 samples)
Execl Throughput 7669.7 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 713151.3 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 213970.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2046170.0 KBps (30.0 s, 2 samples)
Pipe Throughput 1482925.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 431722.7 lps (10.0 s, 7 samples)
Process Creation 24281.1 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 8072.1 lpm (60.2 s, 2 samples)
Shell Scripts (8 concurrent) 1011.4 lpm (60.0 s, 2 samples)
System Call Overhead 1302308.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 22410640.8 1920.4
Double-Precision Whetstone 55.0 3409.7 619.9
Execl Throughput 43.0 7669.7 1783.6
File Copy 1024 bufsize 2000 maxblocks 3960.0 713151.3 1800.9
File Copy 256 bufsize 500 maxblocks 1655.0 213970.7 1292.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 2046170.0 3527.9
Pipe Throughput 12440.0 1482925.8 1192.1
Pipe-based Context Switching 4000.0 431722.7 1079.3
Process Creation 126.0 24281.1 1927.1
Shell Scripts (1 concurrent) 42.4 8072.1 1903.8
Shell Scripts (8 concurrent) 6.0 1011.4 1685.7
System Call Overhead 15000.0 1302308.4 868.2
========
System Benchmarks Index Score 1490.8
/proc/cpuinfo:
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 58
model name : Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz
stepping : 9
cpu MHz : 3392.295
cache size : 8192 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 13
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss nx rdtscp lm constant_tsc up arch_perfmon pebs bts xtopology tsc_reliable nonstop_tsc aperfmperf pni pclmulqdq ssse3 cx16 sse4_1 sse4_2 popcnt aes hypervisor lahf_lm ida arat
bogomips : 6784.59
clflush size : 64
cache_alignment : 64
address sizes : 40 bits physical, 48 bits virtual
power management:
/proc/meminfo:
MemTotal: 514636 kB
MemFree: 34160 kB
Buffers: 70136 kB
Cached: 371244 kB
SwapCached: 0 kB
Active: 244608 kB
Inactive: 203144 kB
Active(anon): 272 kB
Inactive(anon): 6200 kB
Active(file): 244336 kB
Inactive(file): 196944 kB
Unevictable: 0 kB
Mlocked: 0 kB
HighTotal: 0 kB
HighFree: 0 kB
LowTotal: 514636 kB
LowFree: 34160 kB
SwapTotal: 1003512 kB
SwapFree: 1003512 kB
Dirty: 0 kB
Writeback: 0 kB
AnonPages: 6372 kB
Mapped: 6964 kB
Shmem: 100 kB
Slab: 28556 kB
SReclaimable: 24084 kB
SUnreclaim: 4472 kB
KernelStack: 456 kB
PageTables: 372 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
CommitLimit: 1260828 kB
Committed_AS: 38636 kB
VmallocTotal: 503800 kB
VmallocUsed: 6388 kB
VmallocChunk: 489240 kB
HardwareCorrupted: 0 kB
HugePages_Total: 0
HugePages_Free: 0
HugePages_Rsvd: 0
HugePages_Surp: 0
Hugepagesize: 4096 kB
DirectMap4k: 16384 kB
DirectMap4M: 507904 kB
Like expected, CPU much faster, but node is obvisiously oversold and network is quiet bad
Last edited: